Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96059
    Prev
    Next
    INDEX
    Explanations

    references and citations in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    902
    -0.07
    atu
    -0.07
    etr
    -0.06
    ioc
    -0.06
    owel
    -0.06
     recre
    -0.06
    agu
    -0.06
    abs
    -0.06
    gio
    -0.06
    anza
    -0.06
    POSITIVE LOGITS
    portlet
    0.07
    kaar
    0.07
    ÑĢеÑĤÑĮ
    0.06
    urgeon
    0.06
    imler
    0.06
    UPER
    0.06
    linkplain
    0.06
    #aa
    0.06
    OLOR
    0.06
    asio
    0.06
    Activations Density 0.000%

    No Known Activations